Borrowing it
Nothing to install: this file belongs to choyiny/saasmail. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/choyiny/saasmail/main/.claude/skills/update-saasmail/SKILL.mdgit clone --depth 1 https://github.com/choyiny/saasmailWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/choyiny/saasmail/update-saasmail)<a href="https://agentmods.dev/skills/choyiny/saasmail/update-saasmail"><img src="https://agentmods.dev/badge/skills/choyiny/saasmail/update-saasmail/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/choyiny/saasmail/update-saasmail"><img src="https://agentmods.dev/badge/skills/choyiny/saasmail/update-saasmail.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 65 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00121 | $0.02097 |
| Opus 5.5 | $0.00048 | $0.00839 |
| Sonnet 5.5 | $0.00024 | $0.00419 |
| Haiku 4.5 | $0.00012 | $0.00210 |
Grade A, and why
update-saasmail scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 157 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Update saasmail
Two paths. Pick by how the instance was installed:
- Installed with
npx saasmail install(state in~/.saasmail/<slug>/, orSAASMAIL_HOME): follow Upgrade from npm. - Installed from a clone (
yarn saasmail install, state in the checkout's.saasmail/), or a fork or modified code the user keeps running from a clone: follow Sync a fork from upstream (below).
Ask if unsure. Never deploy from a clone with yarn deploy for an install the package owns.
Upgrade from npm
upgrade is npm-only; run it from any directory. Same rule as onboarding: you run the read-only plan, the user runs the apply in their own terminal, not with !, because the apply prints the setup code and credential prompts must stay out of this conversation.
-
npx saasmail status [--name <name>]shows the recorded install, the running version and Latest on npm. -
Plan (read-only, safe from your shell):
npx saasmail@latest upgrade --plan [--name <name>]Walk the user through it: new migrations, resources and secrets, and the plan digest. Say plainly that migrations cannot be undone; if a release is broken, the way back is the next release.
-
It stops, changing nothing, in two cases:
- Downgrade: the site runs a newer version than the package. Tell the user the version it names; never work around it.
- Custom code: the running version is not a release (a modified fork, a dirty or diverged commit, or unknown). Ask explicitly whether they want to replace it. Only on a clear yes, the plan and apply get
--replace-custom-code.
-
Ask for an explicit yes, then give the user the apply command the plan printed (it ends with
--expect-plan <digest> --yes) to run in their own terminal. -
If it fails, the message prints the command to continue. Ask for the error lines (never a
Setup code:line), help fix the cause, and have them runnpx saasmail@latest upgrade --resume [--name <name>]in their terminal.--resumecontinues even if the site is down. "The plan changed since it was reviewed" means something moved: plan again. -
Run
npx saasmail status [--name <name>]yourself and confirm the running version matches Latest.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 9d ago Changed · -8 lines · -9 tokens per session 8c74fd2b5ea0
- 18d ago Changed 5fb49d4958d7
- 19d ago Changed · +37 lines · +25 tokens per session ce7221368ea9
- 21d ago Changed · +2 lines 4492ae9c074f
- 2mo ago First seen · 126 lines · 105 tokens per session scan A 82dcba5061ce
update-saasmail is a skill published in the GitHub repository choyiny/saasmail (274 stars, last pushed 4d ago), licensed Apache-2.0. It adds 121 tokens to every session and 2,097 once invoked, about $0.0005 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
update-saasmail compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| update-saasmailchoyiny/saasmail | Skill | 274 | 4d ago | Apache-2.0 | A | 121 | Claude Code |
| platform-deliveryheymegabyte/claude-skills | Skill | 22 | 1mo ago | none | A | 37 | Claude Code |
| moemailbeilunyang/moemail | Skill | 2.8k | 2mo ago | MIT | A | 37 | Claude Code, Codex |
| agentifytokencanopy/e2a | Skill | 198 | 4d ago | Apache-2.0 | A | 93 | Claude Code |
| autonomous-repotokencanopy/e2a | Skill | 198 | 4d ago | Apache-2.0 | A | 64 | Claude Code |
| skills-updatelouisbrulenaudet/monorepo-template | Skill | 19 | 5d ago | Apache-2.0 | A | 75 | Claude Code, Codex |
| changesetlouisbrulenaudet/monorepo-template | Skill | 19 | 5d ago | Apache-2.0 | A | 87 | Claude Code, Codex |